Crash/Error using Biologically-inspired Dataset split #109
Unanswered
CarrieASims
asked this question in
Q&A
Replies: 1 comment 2 replies
-
Hi CarrieASims, This is a bug of some recent changes. I suggest that you export the dataset without using this option. If the problem remains, let us know. |
Beta Was this translation helpful? Give feedback.
2 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
TagLab is crashing when I try to run the Biologically-Inspired dataset split when Exporting a New Training Dataset
This is the error:
PS E:\5_Taglab\TagLab-2022.11.3> py taglab.py
TagLab 2023.5.17
Traceback (most recent call last):
File "E:\5_Taglab\TagLab-2022.11.3\taglab.py", line 4060, in exportNewDataset
new_dataset.setupAreas(mode.upper(), target_classes)
File "E:\5_Taglab\TagLab-2022.11.3\source\NewDataset.py", line 667, in setupAreas
val_area, test_area = self.findAreas(target_classes=target_classes)
File "E:\5_Taglab\TagLab-2022.11.3\source\NewDataset.py", line 397, in findAreas
landscape_number, landscape_coverage, landscape_PSCV = self.calculateMetrics([0, 0, map_w, map_h], target_classes)
File "E:\5_Taglab\TagLab-2022.11.3\source\NewDataset.py", line 291, in calculateMetrics
if self.frequencies[key] > 0.0:
KeyError: (0, 'Background')
PS E:\5_Taglab\TagLab-2022.11.3>
I have limited understanding but seems it has an issue with the class Background, which is set default as Empty in the TagLab interface.
Any assistance/enlightenment is most appreciated.
thanks
Beta Was this translation helpful? Give feedback.
All reactions